Efficient MedSAMs: Segment Anything in Medical Images on Laptop

Autor: Ma, Jun, Li, Feifei, Kim, Sumin, Asakereh, Reza, Le, Bao-Hiep, Nguyen-Vu, Dang-Khoa, Pfefferle, Alexander, Wei, Muxin, Gao, Ruochen, Lyu, Donghang, Yang, Songxiao, Purucker, Lennart, Marinov, Zdravko, Staring, Marius, Lu, Haisheng, Dao, Thuy Thanh, Ye, Xincheng, Li, Zhi, Brugnara, Gianluca, Vollmuth, Philipp, Foltyn-Dumitru, Martha, Cho, Jaeyoung, Mahmutoglu, Mustafa Ahmed, Bendszus, Martin, Pflüger, Irada, Rastogi, Aditya, Ni, Dong, Yang, Xin, Zhou, Guang-Quan, Wang, Kaini, Heller, Nicholas, Papanikolopoulos, Nikolaos, Weight, Christopher, Tong, Yubing, Udupa, Jayaram K, Patrick, Cahill J., Wang, Yaqi, Zhang, Yifan, Contijoch, Francisco, McVeigh, Elliot, Ye, Xin, He, Shucheng, Haase, Robert, Pinetz, Thomas, Radbruch, Alexander, Krause, Inga, Kobler, Erich, He, Jian, Tang, Yucheng, Yang, Haichun, Huo, Yuankai, Luo, Gongning, Kushibar, Kaisar, Amankulov, Jandos, Toleshbayev, Dias, Mukhamejan, Amangeldi, Egger, Jan, Pepe, Antonio, Gsaxner, Christina, Luijten, Gijs, Fujita, Shohei, Kikuchi, Tomohiro, Wiestler, Benedikt, Kirschke, Jan S., de la Rosa, Ezequiel, Bolelli, Federico, Lumetti, Luca, Grana, Costantino, Xie, Kunpeng, Wu, Guomin, Puladi, Behrus, Martín-Isla, Carlos, Lekadir, Karim, Campello, Victor M., Shao, Wei, Brisbane, Wayne, Jiang, Hongxu, Wei, Hao, Yuan, Wu, Li, Shuangle, Zhou, Yuyin, Wang, Bo

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice.

Externí odkaz: http://arxiv.org/abs/2412.16085